© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78013
    Prev
    Next
    INDEX
    Explanations

    instances of null values or references in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pill
    -0.07
    onda
    -0.06
    OTH
    -0.06
     coarse
    -0.06
     rot
    -0.06
     indeed
    -0.06
    amb
    -0.06
    esses
    -0.06
    loor
    -0.06
    qual
    -0.06
    POSITIVE LOGITS
    iola
    0.07
     underlying
    0.07
    Äħż
    0.07
    å§
    0.07
    airro
    0.07
    ¼åIJĪ
    0.07
    út
    0.07
    273
    0.06
    ĵåIJį
    0.06
    osoph
    0.06
    Activations Density 0.004%

    No Known Activations